Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: Segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal

Taxonomy of Acute Stroke: Imaging, Processing, and Treatment

Stroke management employs a variety of diagnostic imaging modalities, image processing and analysis methods, and treatment procedures. This work categorizes methods for stroke imaging, image processing and analysis, and treatment, and provides their taxonomies illustrated by a state-of-the-art review. Imaging plays a critical role in stroke management, and the most frequently employed modalities are computed tomography (CT) and magnetic resonance (MR). CT includes unenhanced non-contrast CT as the first-line diagnosis, CT angiography, and CT perfusion. MR is the most complete method to examine stroke patients. MR angiography is useful to evaluate the severity of artery stenosis, vascular occlusion, and collateral flow. Diffusion-weighted imaging is the gold standard for evaluating ischemia. MR perfusion-weighted imaging assesses the penumbra. The stroke image processing methods are divided into non-atlas/template-based and atlas/template-based. The non-atlas/template-based methods are subdivided into intensity and contrast transformations, local segmentation-related, anatomy-guided, global density-guided, and artificial intelligence/deep learning-based. The atlas/template-based methods are subdivided into intensity templates and atlases with three atlas types: anatomy atlases, vascular atlases, and lesion-derived atlases. The treatment procedures for arterial and venous strokes include intravenous and intraarterial thrombolysis and mechanical thrombectomy. This work captures the state-of-the-art in stroke management summarized in the form of comprehensive and straightforward taxonomy diagrams. All three introduced taxonomies in diagnostic imaging, image processing and analysis, and treatment are widely illustrated and compared against other state-of-the-art classifications.

Development of statistical auto-segmentation method for diffusion restriction gray matter lesions in patients with newly diagnosed sporadic Creutzfeldt-Jakob disease

Quantification of diffusion restriction lesions in sporadic Creutzfeldt-Jakob disease (sCJD) may provide information of the disease burden. We aim to develop an automatic segmentation model for sCJD and to evaluate the volume of disease extent as a prognostic marker for overall survival. Fifty-six patients (mean age ± SD, 61.2 ± 9.9 years) were included from February 2000 to July 2020. A threshold-based segmentation was used to obtain abnormal signal intensity masks. Segmented volumes were compared with the visual grade. The Dice similarity coefficient was calculated to measure the similarity between the automatic vs. manual segmentation. Cox proportional hazards regression analysis was performed to evaluate the volume of disease extent as a prognostic marker. The automatic segmentation showed good correlation with the visual grading. The cortical lesion volumes significantly increased as the visual grade aggravated (extensive: 112.9 ± 73.2; moderate: 45.4 ± 30.4; minimal involvement: 29.6 ± 18.1 mm3) (P < 0.001). The deep gray matter lesion volumes were significantly higher for positive than for negative involvement of the deep gray matter (5.6 ± 4.6 mm3 vs. 1.0 ± 1.3 mm3, P < 0.001). The mean Dice similarity coefficients were 0.90 and 0.94 for cortical and deep gray matter lesions, respectively. However, the volume of disease extent was not associated with worse overall survival (cortical extent: P = 0.07; deep gray matter extent: P = 0.12).

Providing clinical context to the spatio-temporal analysis of 4D CT perfusion to predict acute ischemic stroke lesion outcomes

Acute ischemic stroke is a leading cause of mortality and morbidity worldwide. Timely identification of the extent of a stroke is crucial for effective treatment, whereas spatio-temporal (4D) Computed Tomography Perfusion (CTP) imaging is playing a critical role in this process. Recently, the first deep learning-based methods that leverage the full spatio-temporal nature of perfusion imaging for predicting stroke lesion outcomes have been proposed. However, clinical information is typically not integrated into the learning process, which may be helpful to improve the tissue outcome prediction given the known influence of various factors (i.e., physiological, demographic, and treatment factors) on lesion growth. Cross-attention, a multimodal fusion strategy, has been successfully used to combine information from multiple sources, but it has yet to be applied to stroke lesion outcome prediction. Therefore, this work aimed to develop and evaluate a novel multimodal and spatio-temporal deep learning model that utilizes cross-attention to combine information from 4D CTP and clinical metadata simultaneously to predict stroke lesion outcomes. The proposed model was evaluated using a dataset of 70 acute ischemic stroke patients, demonstrating significantly improved volume estimates (mean error = 19 ml) compared to a baseline unimodal approach (mean error = 35 ml, p< 0.05). The proposed model allows generating attention maps and counterfactual outcome scenarios to investigate the relevance of clinical variables in predicting stroke lesion outcomes at a patient level, helping to provide a better understanding of the model's decision-making process.

The impact of brain lesions on tDCS-induced electric fields

Transcranial direct current stimulation (tDCS) can enhance motor and language rehabilitation after stroke. Though brain lesions distort tDCS-induced electric field (E-field), systematic accounts remain limited. Using electric field modelling, we investigated the effect of 630 synthetic lesions on E-field magnitude in the region of interest (ROI). Models were conducted for two tDCS montages targeting either primary motor cortex (M1) or Broca's area (BA44). Absolute E-field magnitude in the ROI differed by up to 42% compared to the non-lesioned brain depending on lesion size, lesion-ROI distance, and lesion conductivity value. Lesion location determined the sign of this difference: lesions in-line with the predominant direction of current increased E-field magnitude in the ROI, whereas lesions located in the opposite direction decreased E-field magnitude. We further explored how individualised tDCS can control lesion-induced effects on E-field. Lesions affected the individualised electrode configuration needed to maximise E-field magnitude in the ROI, but this effect was negligible when prioritising the maximisation of radial inward current. Lesions distorting tDCS-induced E-field, is likely to exacerbate inter-individual variability in E-field magnitude. Individualising electrode configuration and stimulator output can minimise lesion-induced variability but requires improved estimates of lesion conductivity. Individualised tDCS is critical to overcome E-field variability in lesioned brains.

Neuroimaging Modalities Used for Ischemic Stroke Diagnosis and Monitoring

Strokes are one of the global leading causes of physical or mental impairment and fatality, classified into hemorrhagic and ischemic strokes. Ischemic strokes happen when a thrombus blocks or plugs an artery and interrupts or reduces blood supply to the brain tissue. Deciding on the imaging modality which will be used for stroke detection depends on the expertise and availability of staff and the infrastructure of hospitals. Magnetic resonance imaging provides valuable information, and its sensitivity for smaller infarcts is greater, while computed tomography is more extensively used, since it can promptly exclude acute cerebral hemorrhages and is more favorable speed-wise. The aim of this article was to give information about the neuroimaging modalities used for the diagnosis and monitoring of ischemic strokes. We reviewed the available literature and presented the use of computed tomography, CT angiography, CT perfusion, magnetic resonance imaging, MR angiography and MR perfusion for the detection of ischemic strokes and their monitoring in different phases of stroke development.

Deep learning-based automated lesion segmentation on mouse stroke magnetic resonance images

Magnetic resonance imaging (MRI) is widely used for ischemic stroke lesion detection in mice. A challenge is that lesion segmentation often relies on manual tracing by trained experts, which is labor-intensive, time-consuming, and prone to inter- and intra-rater variability. Here, we present a fully automated ischemic stroke lesion segmentation method for mouse T2-weighted MRI data. As an end-to-end deep learning approach, the automated lesion segmentation requires very little preprocessing and works directly on the raw MRI scans. We randomly split a large dataset of 382 MRI scans into a subset (n = 293) to train the automated lesion segmentation and a subset (n = 89) to evaluate its performance. We compared Dice coefficients and accuracy of lesion volume against manual segmentation, as well as its performance on an independent dataset from an open repository with different imaging characteristics. The automated lesion segmentation produced segmentation masks with a smooth, compact, and realistic appearance that are in high agreement with manual segmentation. We report dice scores higher than the agreement between two human raters reported in previous studies, highlighting the ability to remove individual human bias and standardize the process across research studies and centers.

Automated estimation of ischemic core volume on noncontrast-enhanced CT via machine learning

BACKGROUND

Accurate estimation of ischemic core on baseline imaging has treatment implications in patients with acute ischemic stroke (AIS). Machine learning (ML) algorithms have shown promising results in estimating ischemic core using routine noncontrast computed tomography (NCCT).

OBJECTIVE

We used an ML-trained algorithm to quantify ischemic core volume on NCCT in a comparative analysis to pretreatment magnetic resonance imaging (MRI) diffusion-weighted imaging (DWI) in patients with AIS.

METHODS

Patients with AIS who had both pretreatment NCCT and MRI were enrolled. An automatic segmentation ML approach was applied using Brainomix software (Oxford, UK) to segment the ischemic voxels and calculate ischemic core volume on NCCT. Ischemic core volume was also calculated on baseline MRI DWI. Comparative analysis was performed using Bland-Altman plots and Pearson correlation.

RESULTS

A total of 72 patients were included. The time-to-stroke onset time was 134.2/89.5 minutes (mean/median). The time difference between NCCT and MRI was 64.8/44.5 minutes (mean/median). In patients who presented within 1 hour from stroke onset, the ischemic core volumes were significantly (p  =  0.005) underestimated by ML-NCCT. In patients presented beyond 1 hour, the ML-NCCT estimated ischemic core volumes approximated those obtained by MRI-DWI and with significant correlation (r  =  0.56, p < 0.001).

CONCLUSION

The ischemic core volumes calculated by the described ML approach on NCCT approximate those obtained by MRI in patients with AIS who present beyond 1 hour from stroke onset.

Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography

A non-contrast cranial computer tomography (ncCT) is often employed for the diagnosis of the early stage of the ischemic stroke. However, the number of false negatives is high. More accurate results are obtained by an MRI. However, the MRI is not available in every hospital. Moreover, even if it is available in the clinic for the routine tests, emergency often does not have it. Therefore, this paper proposes an end-to-end framework for detection and segmentation of the brain infarct on the ncCT. The computer tomography perfusion (CTp) is used as the ground truth. The proposed ensemble model employs three deep convolution neural networks (CNNs) to process three end-to-end feature maps and a hand-craft features characterized by specific contra-lateral features. To improve the accuracy of the detected infarct area, the spatial dependencies between neighboring slices are employed at the postprocessing step. The numerical experiments have been performed on 18 ncCT-CTp paired stroke cases (804 image-pairs). The leave-one-out approach is applied for evaluating the proposed method. The model achieves 91.16% accuracy, 65.15% precision, 77.44% recall, 69.97% F1 score, and 0.4536 IoU.

Predicting treatment-specific lesion outcomes in acute ischemic stroke from 4D CT perfusion imaging using spatio-temporal convolutional neural networks

For the diagnosis and precise treatment of acute ischemic stroke, predicting the final location and volume of lesions is of great clinical interest. Current deep learning-based prediction methods mainly use perfusion parameter maps, which can be calculated from spatio-temporal (4D) CT perfusion (CTP) imaging data, to estimate the tissue outcome of an acute ischemic stroke. However, this calculation relies on a deconvolution operation, an ill-posed problem requiring strong regularization and definition of an arterial input function. Thus, improved predictions might be achievable if the deep learning models were applied directly to acute 4D CTP data rather than perfusion maps. In this work, a novel deep spatio-temporal convolutional neural network is proposed for predicting treatment-dependent stroke lesion outcomes by making full use of raw 4D CTP data. By merging a U-Net-like architecture with temporal convolutional networks, we efficiently process the spatio-temporal information available in CTP datasets to make a tissue outcome prediction. The proposed method was evaluated on 147 patients using a 10-fold cross validation, which demonstrated that the proposed 3D+time model (mean Dice=0.45) significantly outperforms both a 2D+time variant of our approach (mean Dice=0.43) and a state-of-the-art method that uses perfusion maps (mean Dice=0.38). These results show that 4D CTP datasets include more predictive information than perfusion parameter maps, and that the proposed method is an efficient approach to make use of this complex data.

Towards an Accurate MRI Acute Ischemic Stroke Lesion Segmentation Based on Bioheat Equation and U-Net Model

Acute ischemic stroke represents a cerebrovascular disease, for which it is practical, albeit challenging to segment and differentiate infarct core from salvageable penumbra brain tissue. Ischemic stroke causes the variation of cerebral blood flow and heat generation due to metabolism. Therefore, the temperature is modified in the ischemic stroke region. In this paper, we incorporate acute ischemic stroke temperature profile to reinforce segmentation accuracy in MRI. Pennes bioheat equation was used to generate brain thermal images that may provide rich information regarding the temperature change in acute ischemic stroke lesions. The thermal images were generated by calculating the temperature of the brain with acute ischemic stroke. Then, U-Net was used in this paper for the segmentation of acute ischemic stroke. A dataset of 3192 images was created to train U-Net using k-fold crossvalidation. The training time was about 10 hours and 35 minutes in NVIDIA GPU. Next, the obtained trained model was compared with recent methods to analyze the effect of the ischemic stroke temperature profile in segmentation. The obtained results show that significant parts of acute ischemic stroke and background areas are segmented only in thermal images, which proves the importance of using thermal information to improve the segmentation outcomes in MRI diagnosis.

Prediction of Tissue Damage Using a User-Independent Machine Learning Algorithm vs. Tmax Threshold Maps

(1) Background: To test the accuracy of a fully automated stroke tissue estimation algorithm (FASTER) to predict final lesion volumes in an independent dataset in patients with acute stroke; (2) Methods: Tissue-at-risk prediction was performed in 31 stroke patients presenting with a proximal middle cerebral artery occlusion. FDA-cleared perfusion software using the AHA recommendation for the Tmax threshold delay was tested against a prediction algorithm trained on an independent perfusion software using artificial intelligence (FASTER). Following our endovascular strategy to consequently achieve TICI 3 outcome, we compared patients with complete reperfusion (TICI 3) vs. no reperfusion (TICI 0) after mechanical thrombectomy. Final infarct volume was determined on a routine follow-up MRI or CT at 90 days after the stroke; (3) Results: Compared to the reference standard (infarct volume after 90 days), the decision forest algorithm overestimated the final infarct volume in patients without reperfusion. Underestimation was observed if patients were completely reperfused. In cases where the FDA-cleared segmentation was not interpretable due to improper definitions of the arterial input function, the decision forest provided reliable results; (4) Conclusions: The prediction accuracy of automated tissue estimation depends on (i) success of reperfusion, (ii) infarct size, and (iii) software-related factors introduced by the training sample. A principal advantage of machine learning algorithms is their improved robustness to artifacts in comparison to solely threshold-based model-dependent software. Validation on independent datasets remains a crucial condition for clinical implementations of decision support systems in stroke imaging.

BRAIN STROKE DETECTION USING TENSOR FACTORIZATION AND MACHINE LEARNING MODELS

Stroke is one of the foremost common disorders among the elderly. Early detection of stroke from Magnetic Resonance Imaging (MRI) is typically based on the representation method of these images. Representing MRI slices in two dimensional structures (matrices) implies ignoring the dependencies between these slices. Additionally, to combine all features exist in these slices requires more computations and time. However, this results in inexact diagnosis. In this paper, we propose a new tensor-based approach for stroke detection from MRI. The proposed methodology has two phases. In first phase, each patient’s MRI are represented as a tensor. Tensor representations are powerful because they capture the dependencies in high-dimensional data, MRI of patient, which gives more reliable and accurate results. Also, tensor factorization is used as a method for feature extraction and reduction, which improves the performance and accuracy of classifiers. In second phase, these extracted features are used to train support vector machine (SVM) and XGBoost classifiers to classify MRI images into normal and abnormal. The proposed method is assessed with MRI dataset, and the conducted experiments illustrate the efficiency of this approach. It achieves classification accuracy of 98%.

Fusion of Higher Order Spectra and Texture Extraction Methods for Automated Stroke Severity Classification with MRI Images

This paper presents a scientific foundation for automated stroke severity classification. We have constructed and assessed a system which extracts diagnostically relevant information from Magnetic Resonance Imaging (MRI) images. The design was based on 267 images that show the brain from individual subjects after stroke. They were labeled as either Lacunar Syndrome (LACS), Partial Anterior Circulation Syndrome (PACS), or Total Anterior Circulation Stroke (TACS). The labels indicate different physiological processes which manifest themselves in distinct image texture. The processing system was tasked with extracting texture information that could be used to classify a brain MRI image from a stroke survivor into either LACS, PACS, or TACS. We analyzed 6475 features that were obtained with Gray-Level Run Length Matrix (GLRLM), Higher Order Spectra (HOS), as well as a combination of Discrete Wavelet Transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) methods. The resulting features were ranked based on the p-value extracted with the Analysis Of Variance (ANOVA) algorithm. The ranked features were used to train and test four types of Support Vector Machine (SVM) classification algorithms according to the rules of 10-fold cross-validation. We found that SVM with Radial Basis Function (RBF) kernel achieves: Accuracy (ACC) = 93.62%, Specificity (SPE) = 95.91%, Sensitivity (SEN) = 92.44%, and Dice-score = 0.95. These results indicate that computer aided stroke severity diagnosis support is possible. Such systems might lead to progress in stroke diagnosis by enabling healthcare professionals to improve diagnosis and management of stroke patients with the same resources.

Artificial intelligence in clinical decision support and outcome prediction - applications in stroke

Artificial intelligence (AI) is making a profound impact in healthcare, with the number of AI applications in medicine increasing substantially over the past five years. In acute stroke, it is playing an increasingly important role in clinical decision-making. Contemporary advances have increased the amount of information - both clinical and radiological - which clinicians must consider when managing patients. In the time-critical setting of acute stroke, AI offers the tools to rapidly evaluate and consolidate available information, extracting specific predictions from rich, noisy data. It has been applied to the automatic detection of stroke lesions on imaging and can guide treatment decisions through the prediction of tissue outcomes and long-term functional outcomes. This review examines the current state of AI applications in stroke, exploring their potential to reform stroke care through clinical decision support, as well as the challenges and limitations which must be addressed to facilitate their acceptance and adoption for clinical use.

EIS-Net: Segmenting early infarct and scoring ASPECTS simultaneously on non-contrast CT of patients with acute ischemic stroke

Detecting early infarct (EI) plays an essential role in patient selection for reperfusion therapy in the management of acute ischemic stroke (AIS). EI volume at acute or hyper-acute stage can be measured using advanced pre-treatment imaging, such as MRI and CT perfusion. In this study, a novel multi-task learning approach, EIS-Net, is proposed to segment EI and score Alberta Stroke Program Early CT Score (ASPECTS) simultaneously on baseline non-contrast CT (NCCT) scans of AIS patients. The EIS-Net comprises of a 3D triplet convolutional neural network (T-CNN) for EI segmentation and a multi-region classification network for ASPECTS scoring. T-CNN has triple encoders with original NCCT, mirrored NCCT, and atlas as inputs, as well as one decoder. A comparison disparity block (CDB) is designed to extract and enhance image contexts. In the decoder, a multi-level attention gate module (MAGM) is developed to recalibrate the features of the decoder for both segmentation and classification tasks. Evaluations using a high-quality dataset comprising of baseline NCCT and concomitant diffusion weighted MRI (DWI) as reference standard of 260 patients with AIS show that the proposed EIS-Net can accurately segment EI. The EIS-Net segmented EI volume strongly correlates with EI volume on DWI (r=0.919), and the mean difference between the two volumes is 8.5 mL. For ASPECTS scoring, the proposed EIS-Net achieves an intraclass correlation coefficient of 0.78 for total 10-point ASPECTS and a kappa of 0.75 for dichotomized ASPECTS (≤ 4 vs. >4). Both EI segmentation and ASPECTS scoring tasks achieve state-of-the-art performances.

Ischemic infarct detection, localization, and segmentation in noncontrast CT human brain scans: review of automated methods

Noncontrast Computed Tomography (NCCT) of the brain has been the first-line diagnosis for emergency evaluation of acute stroke, so a rapid and automated detection, localization, and/or segmentation of ischemic lesions is of great importance. We provide the state-of-the-art review of methods for automated detection, localization, and/or segmentation of ischemic lesions on NCCT in human brain scans along with their comparison, evaluation, and classification. Twenty-two methods are (1) reviewed and evaluated; (2) grouped into image processing and analysis-based methods (11 methods), brain atlas-based methods (two methods), intensity template-based methods (1 method), Stroke Imaging Marker-based methods (two methods), and Artificial Intelligence-based methods (six methods); and (3) properties of these groups of methods are characterized. A new method classification scheme is proposed as a 2 × 2 matrix with local versus global processing and analysis, and density versus spatial sampling. Future studies are necessary to develop more efficient methods directed toward deep learning methods as well as combining the global methods with a high sampling both in space and density for the merged radiologic and neurologic data.

Impact of the reperfusion status for predicting the final stroke infarct using deep learning

BACKGROUND

Predictive maps of the final infarct may help therapeutic decisions in acute ischemic stroke patients. Our objectives were to assess whether integrating the reperfusion status into deep learning models would improve their performance, and to compare them to current clinical prediction methods.

METHODS

We trained and tested convolutional neural networks (CNNs) to predict the final infarct in acute ischemic stroke patients treated by thrombectomy in our center. When training the CNNs, non-reperfused patients from a non-thrombectomized cohort were added to the training set to increase the size of this group. Baseline diffusion and perfusion-weighted magnetic resonance imaging (MRI) were used as inputs, and the lesion segmented on day-6 MRI served as the ground truth for the final infarct. The cohort was dichotomized into two subsets, reperfused and non-reperfused patients, from which reperfusion status specific CNNs were developed and compared to one another, and to the clinically-used perfusion-diffusion mismatch model. Evaluation metrics included the Dice similarity coefficient (DSC), precision, recall, volumetric similarity, Hausdorff distance and area-under-the-curve (AUC).

RESULTS

We analyzed 109 patients, including 35 without reperfusion. The highest DSC were achieved in both reperfused and non-reperfused patients (DSC = 0.44 ± 0.25 and 0.47 ± 0.17, respectively) when using the corresponding reperfusion status-specific CNN. CNN-based models achieved higher DSC and AUC values compared to those of perfusion-diffusion mismatch models (reperfused patients: AUC = 0.87 ± 0.13 vs 0.79 ± 0.17, P < 0.001; non-reperfused patients: AUC = 0.81 ± 0.13 vs 0.73 ± 0.14, P < 0.01, in CNN vs perfusion-diffusion mismatch models, respectively).

CONCLUSION

The performance of deep learning models improved when the reperfusion status was incorporated in their training. CNN-based models outperformed the clinically-used perfusion-diffusion mismatch model. Comparing the predicted infarct in case of successful vs failed reperfusion may help in estimating the treatment effect and guiding therapeutic decisions in selected patients.

Combining unsupervised and supervised learning for predicting the final stroke lesion

Predicting the final ischaemic stroke lesion provides crucial information regarding the volume of salvageable hypoperfused tissue, which helps physicians in the difficult decision-making process of treatment planning and intervention. Treatment selection is influenced by clinical diagnosis, which requires delineating the stroke lesion, as well as characterising cerebral blood flow dynamics using neuroimaging acquisitions. Nonetheless, predicting the final stroke lesion is an intricate task, due to the variability in lesion size, shape, location and the underlying cerebral haemodynamic processes that occur after the ischaemic stroke takes place. Moreover, since elapsed time between stroke and treatment is related to the loss of brain tissue, assessing and predicting the final stroke lesion needs to be performed in a short period of time, which makes the task even more complex. Therefore, there is a need for automatic methods that predict the final stroke lesion and support physicians in the treatment decision process. We propose a fully automatic deep learning method based on unsupervised and supervised learning to predict the final stroke lesion after 90 days. Our aim is to predict the final stroke lesion location and extent, taking into account the underlying cerebral blood flow dynamics that can influence the prediction. To achieve this, we propose a two-branch Restricted Boltzmann Machine, which provides specialized data-driven features from different sets of standard parametric Magnetic Resonance Imaging maps. These data-driven feature maps are then combined with the parametric Magnetic Resonance Imaging maps, and fed to a Convolutional and Recurrent Neural Network architecture. We evaluated our proposal on the publicly available ISLES 2017 testing dataset, reaching a Dice score of 0.38, Hausdorff Distance of 29.21 mm, and Average Symmetric Surface Distance of 5.52 mm.

Separability of Acute Cerebral Infarction Lesions in CT Based Radiomics: Toward Artificial Intelligence-Assisted Diagnosis

This study aims at analyzing the separability of acute cerebral infarction lesions which were invisible in CT. 38 patients, who were diagnosed with acute cerebral infarction and performed both CT and MRI, and 18 patients, who had no positive finding in either CT or MRI, were enrolled. Comparative studies were performed on lesion and symmetrical regions, normal brain and symmetrical regions, lesion, and normal brain regions. MRI was reconstructed and affine transformed to obtain accurate lesion position of CT. Radiomic features and information gain were introduced to capture efficient features. Finally, 10 classifiers were established with selected features to evaluate the effectiveness of analysis. 1301 radiomic features were extracted from candidate regions after registration. For lesion and their symmetrical regions, there were 280 features with information gain greater than 0.1 and 2 features with information gain greater than 0.3. The average classification accuracy was 0.6467, and the best classification accuracy was 0.7748. For normal brain and their symmetrical regions, there were 176 features with information gain greater than 0.1, 1 feature with information gain greater than 0.2. The average classification accuracy was 0.5414, and the best classification accuracy was 0.6782. For normal brain and lesions, there were 501 features with information gain greater than 0.1 and 1 feature with information gain greater than 0.5. The average classification accuracy was 0.7480, and the best classification accuracy was 0.8694. In conclusion, the study captured significant features correlated with acute cerebral infarction and confirmed the separability of acute lesions in CT, which established foundation for further artificial intelligence-assisted CT diagnosis.

Ensembled liver cancer detection and classification using CT images

Computed tomography (CT) images are commonly used to diagnose liver disease. It is sometimes very difficult to comment on the type, category and level of the tumor, even for experienced radiologists, directly from the CT image, due to the varying intensities. In recent years, it has been important to design and develop computer-assisted imaging techniques to help doctors/physicians improve their diagnosis. The proposed work is to detect the presence of a tumor region in the liver and classify the different stages of the tumor from CT images. CT images of the liver have been classified between normal and tumor classes. In addition, CT images of the tumor have been classified between Hepato Cellular Carcinoma (HCC) and Metastases (MET). The performance of six different classifiers was evaluated on different parameters. The accuracy achieved for different classifiers varies between 98.39% and 100% for tumor identification and between 76.38% and 87.01% for tumor classification. To further, improve performance, a multi-level ensemble model is developed to detect a tumor (liver cancer) and to classify between HCC and MET using features extracted from CT images. The k-fold cross-validation (CV) is also used to justify the robustness of the classifiers. Compared to the individual classifier, the multi-level ensemble model achieved high accuracy in both the detection and classification of different tumors. This study demonstrates automated tumor characterization based on liver CT images and will assist the radiologist in detecting and classifying different types of tumors at a very early stage.

Automated stroke lesion segmentation in non-contrast CT scans using dense multi-path contextual generative adversarial network

Stroke lesion volume is a key radiologic measurement in assessing prognosis of acute ischemic stroke (AIS) patients. The aim of this paper is to develop an automated segmentation method for accurately segmenting follow-up ischemic and hemorrhagic lesion from multislice non-contrast CT (NCCT) volumes of AIS patients. This paper proposes a 2D dense multi-path contextual generative adversarial network (MPC-GAN) where a dense multi-path 2D U-Net is utilized as the generator and a discriminator network is applied to regularize the generator. Contextual information (i.e. bilateral intensity difference, distance map and lesion location probability) are input into the generator and discriminator. The proposed method is validated separately on follow-up NCCT volumes of 60 patients with ischemic infarcts and NCCT volumes of 70 patients with hemorrhages. Quantitative results demonstrated that the proposed MPC-GAN method obtained a Dice coefficient (DC) of 70.6% for ischemic infarct segmentation and a DC of 76.5% for hemorrhage segmentation compared with manual segmented lesions, outperforming several benchmark methods. Additional volumetric analyses demonstrated that the MPC-GAN segmented lesion volume correlated well with manual measurements (Pearson correlation coefficients were 0.926 and 0.927 for ischemic infarcts and hemorrhages, respectively). The proposed MPC-GAN method can accurately segment ischemic infarcts and hemorrhages from NCCT volumes of AIS patients.

Predicting Clinical Outcome in Acute Ischemic Stroke Using Parallel Multi-parametric Feature Embedded Siamese Network

Stroke is the second leading cause of death and disability worldwide, with ischemic stroke as the most common type. The preferred diagnostic procedure at the acute stage is the acquisition of multi-parametric magnetic resonance imaging (MRI). This type of imaging not only detects and locates the stroke lesion, but also provides the blood flow dynamics that helps clinicians in assessing the risks and benefits of reperfusion therapies. However, evaluating the outcome of these risky therapies beforehand is a complicated task due to the variability of lesion location, size, shape, and cerebral hemodynamics involved. Though the fully automated model for predicting treatment outcomes using multi-parametric imaging would be highly valuable in clinical settings, MRI datasets acquired at the acute stage are mostly scarce and suffer high class imbalance. In this paper, parallel multi-parametric feature embedded siamese network (PMFE-SN) is proposed that can learn with few samples and can handle skewness in multi-parametric MRI data. Moreover, five suitable evaluation metrics that are insensitive to imbalance are defined for this problem. The results show that PMFE-SN not only outperforms other state-of-the-art techniques in all these metrics but also can predict the class with a small number of samples, as well as the class with high number of samples. An accuracy of 0.67 on leave one cross out testing has been achieved with only two samples (minority class) for training and accuracy of 0.61 with the highest number of samples (majority class). In comparison, state-of-the-art using hand crafted features has 0 accuracy for minority class and 0.33 accuracy for majority class.

Acute and sub-acute stroke lesion segmentation from multimodal MRI

BACKGROUND AND OBJECTIVE

Acute stroke lesion segmentation tasks are of great clinical interest as they can help doctors make better informed time-critical treatment decisions. Magnetic resonance imaging (MRI) is time demanding but can provide images that are considered the gold standard for diagnosis. Automated stroke lesion segmentation can provide with an estimate of the location and volume of the lesioned tissue, which can help in the clinical practice to better assess and evaluate the risks of each treatment.

METHODS

We propose a deep learning methodology for acute and sub-acute stroke lesion segmentation using multimodal MR imaging. We pre-process the data to facilitate learning features based on the symmetry of brain hemispheres. The issue of class imbalance is tackled using small patches with a balanced training patch sampling strategy and a dynamically weighted loss function. Moreover, a combination of whole patch predictions, using a U-Net based CNN architecture, and high degree of overlapping patches reduces the need for additional post-processing.

RESULTS

The proposed method is evaluated using two public datasets from the 2015 Ischemic Stroke Lesion Segmentation challenge (ISLES 2015). These involve the tasks of sub-acute stroke lesion segmentation (SISS) and acute stroke penumbra estimation (SPES) from multiple diffusion, perfusion and anatomical MRI modalities. The performance is compared against state-of-the-art methods with a blind online testing set evaluation on each of the challenges. At the time of submitting this manuscript, our approach is the first method in the online rankings for the SISS (DSC=0.59 ± 0.31) and SPES sub-tasks (DSC=0.84 ± 0.10). When compared with the rest of submitted strategies, we achieve top rank performance with a lower Hausdorff distance.

CONCLUSIONS

Better segmentation results are obtained by leveraging the anatomy and pathophysiology of acute stroke lesions and using a combined approach to minimize the effects of class imbalance. The same training procedure is used for both tasks, showing the proposed methodology can generalize well enough to deal with different unrelated tasks and imaging modalities without hyper-parameter tuning. In order to promote the reproducibility of our results, a public version of the proposed method has been released to the scientific community.

CSNet: A new DeepNet framework for ischemic stroke lesion segmentation

BACKGROUND AND OBJECTIVES

Acute stroke lesion segmentation is of paramount importance as it can aid medical personnel to render a quicker diagnosis and administer consequent treatment. Automation of this task is technically exacting due to the variegated appearance of lesions and their dynamic development, medical discrepancies, unavailability of datasets, and the requirement of several MRI modalities for imaging. In this paper, we propose a composite deep learning model primarily based on the self-similar fractal networks and the U-Net model for performing acute stroke diagnosis tasks automatically to assist as well as expedite the decision-making process of medical practitioners.

METHODS

We put forth a new deep learning architecture, the Classifier-Segmenter network (CSNet), involving a hybrid training strategy with a self-similar (fractal) U-Net model, explicitly designed to perform the task of segmentation. In fractal networks, the underlying design strategy is based on the repetitive generation of self-similar fractals in place of residual connections. The U-Net model exploits both spatial as well as semantic information along with parameter sharing for a faster and efficient training process. In this new architecture, we exploit the benefits of both by combining them into one hybrid training scheme and developing the concept of a cascaded architecture, which further enhances the model's accuracy by removing redundant parts from the Segmenter's input. Lastly, a voting mechanism has been employed to further enhance the overall segmentation accuracy.

RESULTS

The performance of the proposed architecture has been scrutinized against the existing state-of-the-art deep learning architectures applied to various biomedical image processing tasks by submission on the publicly accessible web platform provided by the MICCAI Ischemic Stroke Lesion Segmentation (ISLES) challenge. The experimental results demonstrate the superiority of the proposed method when compared to similar submitted strategies, both qualitatively and quantitatively in terms of some of the well known evaluation metrics, such as Accuracy, Dice-Coefficient, Recall, and Precision.

CONCLUSIONS

We believe that our method may find use as a handy tool for doctors to identify the location and extent of irreversibly damaged brain tissue, which is said to be a critical part of the decision-making process in case of an acute stroke.

Automatic spatial estimation of white matter hyperintensities evolution in brain MRI using disease evolution predictor deep neural networks

Previous studies have indicated that white matter hyperintensities (WMH), the main radiological feature of small vessel disease, may evolve (i.e., shrink, grow) or stay stable over a period of time. Predicting these changes are challenging because it involves some unknown clinical risk factors that leads to a non-deterministic prediction task. In this study, we propose a deep learning model to predict the evolution of WMH from baseline to follow-up (i.e., 1-year later), namely "Disease Evolution Predictor" (DEP) model, which can be adjusted to become a non-deterministic model. The DEP model receives a baseline image as input and produces a map called "Disease Evolution Map" (DEM), which represents the evolution of WMH from baseline to follow-up. Two DEP models are proposed, namely DEP-UResNet and DEP-GAN, which are representatives of the supervised (i.e., need expert-generated manual labels to generate the output) and unsupervised (i.e., do not require manual labels produced by experts) deep learning algorithms respectively. To simulate the non-deterministic and unknown parameters involved in WMH evolution, we modulate a Gaussian noise array to the DEP model as auxiliary input. This forces the DEP model to imitate a wider spectrum of alternatives in the prediction results. The alternatives of using other types of auxiliary input instead, such as baseline WMH and stroke lesion loads are also proposed and tested. Based on our experiments, the fully supervised machine learning scheme DEP-UResNet regularly performed better than the DEP-GAN which works in principle without using any expert-generated label (i.e., unsupervised). However, a semi-supervised DEP-GAN model, which uses probability maps produced by a supervised segmentation method in the learning process, yielded similar performances to the DEP-UResNet and performed best in the clinical evaluation. Furthermore, an ablation study showed that an auxiliary input, especially the Gaussian noise, improved the performance of DEP models compared to DEP models that lacked the auxiliary input regardless of the model's architecture. To the best of our knowledge, this is the first extensive study on modelling WMH evolution using deep learning algorithms, which deals with the non-deterministic nature of WMH evolution.

Machine Learning for Detecting Early Infarction in Acute Stroke with Non-Contrast-enhanced CT

Background Identifying the presence and extent of infarcted brain tissue at baseline plays a crucial role in the treatment of patients with acute ischemic stroke (AIS). Patients with extensive infarction are unlikely to benefit from thrombolysis or thrombectomy procedures. Purpose To develop an automated approach to detect and quantitate infarction by using non-contrast-enhanced CT scans in patients with AIS. Materials and Methods Non-contrast-enhanced CT images in patients with AIS (<6 hours from symptom onset to CT) who also underwent diffusion-weighted (DW) MRI within 1 hour after AIS were obtained from May 2004 to July 2009 and were included in this retrospective study. Ischemic lesions manually contoured on DW MRI scans were used as the reference standard. An automatic segmentation approach involving machine learning (ML) was developed to detect infarction. Randomly selected nonenhanced CT images from 157 patients with the lesion labels manually contoured on DW MRI scans were used to train and validate the ML model; the remaining 100 patients independent of the derivation cohort were used for testing. The ML algorithm was quantitatively compared with the reference standard (DW MRI) by using Bland-Altman plots and Pearson correlation. Results In 100 patients in the testing data set (median age, 69 years; interquartile range [IQR]: 59-76 years; 59 men), baseline non-contrast-enhanced CT was performed within a median time of 48 minutes from symptom onset (IQR, 27-93 minutes); baseline MRI was performed a median of 38 minutes (IQR, 24-48 minutes) later. The algorithm-detected lesion volume correlated with the reference standard of expert-contoured lesion volume in acute DW MRI scans (r = 0.76, P < .001). The mean difference between the algorithm-segmented volume (median, 15 mL; IQR, 9-38 mL) and the DW MRI volume (median, 19 mL; IQR, 5-43 mL) was 11 mL (P = .89). Conclusion A machine learning approach for segmentation of infarction on non-contrast-enhanced CT images in patients with acute ischemic stroke showed good agreement with stroke volume on diffusion-weighted MRI scans. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Nael in this issue.

A Hybrid Approach for Sub-Acute Ischemic Stroke Lesion Segmentation Using Random Decision Forest and Gravitational Search Algorithm

BACKGROUND

The sub-acute ischemic stroke is the most basic illnesses reason for death on the planet. We evaluate the impact of segmentation technique during the time of breaking down the capacities of the cerebrum.

OBJECTIVE

The main objective of this paper is to segment the ischemic stroke lesions in Magnetic Resonance (MR) images in the presence of other pathologies like neurological disorder, encephalopathy, brain damage, Multiple sclerosis (MS).

METHODS

In this paper, we utilize a hybrid way to deal with segment the ischemic stroke from alternate pathologies in magnetic resonance (MR) images utilizing Random Decision Forest (RDF) and Gravitational Search Algorithm (GSA). The RDF approach is an effective machine learning approach.

RESULTS

The RDF strategy joins two parameters; they are; the number of trees in the forest and the number of leaves per tree; it runs quickly and proficiently when dealing with vast data. The GSA algorithm is utilized to optimize the RDF data for choosing the best number of trees and the number of leaves per tree in the forest.

CONCLUSION

This paper provides a new hybrid GSA-RDF classifier technique to segment the ischemic stroke lesions in MR images. The experimental results demonstrate that the proposed technique has the Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Bias Error (MBE) ranges are 16.5485 %, 7.2654 %, and 2.4585 %individually. The proposed RDF-GSA algorithm has better precision and execution when compared with the existing ischemic stroke segmentation method.

Delineation of Ischemic Core and Penumbra Volumes from MRI using MSNet Architecture

Medical image analysis tasks like segmentation and detection of injury involving manual interventions usually suffers from high inter-observer variabilities. To carry them out efficiently, various deep neural networks have been proposed recently as they provide much higher and reliable performance than the traditional image processing and manual segmentation methods. Non-invasive and robust quantification of salvageable tissue in acute ischemic stroke i.e., the ischemic penumbra, is critical for interventional stroke therapy. This paper proposes a Multi- Sequence Network (MSNet) architecture for this task. In this architecture, the information from multiple sequences are combined for identification and segmentation of core and penumbra (salvageable tissue) regions of ischemic stroke lesions and was tested on multisequence MRI ischemic lesion dataset of ISLES⁰15. Performance of the proposed architecture, in terms of dice similarity coefficient, sensitivity and specificity are found to be 0.68, 0.805 and 0.99 respectively for the core of the lesion and 0.69, 0.949 and 0.964 respectively for the penumbra region.

Ischemic stroke segmentation in multi-sequence MRI by symmetry determined superpixel based hierarchical clustering

Automated estimation of ischemic stroke evolution across different brain anatomical regions has immense potential to revolutionize stroke treatment. Multi-sequence Magnetic Resonance Imaging (MRI) techniques provide information to characterize abnormal tissues based on their anatomy and physical properties. Asymmetry of the right and left hemispheres of the brain is an important cue for abnormality estimation but using it alone is susceptible to occasional error due to self-asymmetry of the brain. A precise estimate of the symmetry axis is therefore essential for accurate asymmetry identification, which holds the key to the proposed method. The proposed symmetry determined superpixel based hierarchical clustering (SSHC) method initially estimates the lesion from inter-hemispheric asymmetry. This asymmetry further determines the thresholding parameter for hierarchically clustering the superpixels leading to an automated and accurate lesion delineation. A multi-sequence MRI based pipeline also combines the estimations from individual sequences. SSHC is evaluated on different sequences of the Loma Linda University (LLU) dataset with 26 patients and the Ischemic Stroke Lesion Segmentation (ISLES'15) dataset with 28 patients. SSHC eliminates the need for manual determination of threshold for combining the superpixel clusters and is more reliable as it derives the information from the quick estimation of asymmetry. SSHC outperforms the state-of-the-art resulting in a high Dice similarity score of 0.704±0.27 and a recall of 0.85±0.01 which are 6% and 35% respectively higher than the challenge winning method. SSHC thus demonstrates a promising potential in the automated detection of (sub-)acute adult ischemic stroke.

Generalizing post-stroke prognoses from research data to clinical data

Around a third of stroke survivors suffer from acquired language disorders (aphasia), but current medicine cannot predict whether or when they might recover. Prognostic research in this area increasingly draws on datasets associating structural brain imaging data with outcome scores for ever-larger samples of stroke patients. The aim is to learn brain-behaviour trends from these data, and generalize those trends to predict outcomes for new patients. The practical significance of this work depends on the expected breadth of that generalization. Here, we show that these models can generalize across countries and native languages (from British patients tested in English to Chilean patients tested in Spanish), across neuroimaging technology (from MRI to CT), and from scans collected months or years after stroke for research purposes, to scans collected days or weeks after stroke for clinical purposes. Our results suggest one important confound, in attempting to generalize from research data to clinical data, is the delay between scan acquisition and language assessment. This delay is typically small for research data, where scans and assessments are often acquired contemporaneously. But the most natural, clinical application of these predictions will employ acute prognostic factors to predict much longer-term outcomes. We mitigated this confound by projecting the clinical patients' lesions from the time when their scans were acquired, to the time when their language abilities were assessed; with this projection in place, there was strong evidence that prognoses derived from research data generalized equally well to research and clinical data. These results encourage attention to the confounding role that lesion growth may play in other types of lesion-symptom analysis.

Automated segmentation of haematoma and perihaematomal oedema in MRI of acute spontaneous intracerebral haemorrhage

BACKGROUND

Spontaneous intracerebral haemorrhage (SICH) is a common condition with high morbidity and mortality. Segmentation of haematoma and perihaematoma oedema on medical images provides quantitative outcome measures for clinical trials and may provide important markers of prognosis in people with SICH.

METHODS

We take advantage of improved contrast seen on magnetic resonance (MR) images of patients with acute and early subacute SICH and introduce an automated algorithm for haematoma and oedema segmentation from these images. To our knowledge, there is no previously proposed segmentation technique for SICH that utilises MR images directly. The method is based on shape and intensity analysis for haematoma segmentation and voxel-wise dynamic thresholding of hyper-intensities for oedema segmentation.

RESULTS

Using Dice scores to measure segmentation overlaps between labellings yielded by the proposed algorithm and five different expert raters on 18 patients, we observe that our technique achieves overlap scores that are very similar to those obtained by pairwise expert rater comparison. A further comparison between the proposed method and a state-of-the-art Deep Learning segmentation on a separate set of 32 manually annotated subjects confirms the proposed method can achieve comparable results with very mild computational burden and in a completely training-free and unsupervised way.

CONCLUSION

Our technique can be a computationally light and effective way to automatically delineate haematoma and oedema extent directly from MR images. Thus, with increasing use of MR images clinically after intracerebral haemorrhage this technique has the potential to inform clinical practice in the future.

Rosmarinus officinalis L. (rosemary) as therapeutic and prophylactic agent

Rosmarinus officinalis L. (rosemary) is a medicinal plant native to the Mediterranean region and cultivated around the world. Besides the therapeutic purpose, it is commonly used as a condiment and food preservative. R. officinalis L. is constituted by bioactive molecules, the phytocompounds, responsible for implement several pharmacological activities, such as anti-inflammatory, antioxidant, antimicrobial, antiproliferative, antitumor and protective, inhibitory and attenuating activities. Thus, in vivo and in vitro studies were presented in this Review, approaching the therapeutic and prophylactic effects of R. officinalis L. on some physiological disorders caused by biochemical, chemical or biological agents. In this way, methodology, mechanisms, results, and conclusions were described. The main objective of this study was showing that plant products could be equivalent to the available medicines.

Stroke Lesion Outcome Prediction Based on MRI Imaging Combined With Clinical Information

In developed countries, the second leading cause of death is stroke, which has the ischemic stroke as the most common type. The preferred diagnosis procedure involves the acquisition of multi-modal Magnetic Resonance Imaging. Besides detecting and locating the stroke lesion, Magnetic Resonance Imaging captures blood flow dynamics that guides the physician in evaluating the risks and benefits of the reperfusion procedure. However, the decision process is an intricate task due to the variability of lesion size, shape, and location, as well as the complexity of the underlying cerebral hemodynamic process. Therefore, an automatic method that predicts the stroke lesion outcome, at a 3-month follow-up, would provide an important support to the physicians' decision process. In this work, we propose an automatic deep learning-based method for stroke lesion outcome prediction. Our main contribution resides in the combination of multi-modal Magnetic Resonance Imaging maps with non-imaging clinical meta-data: the thrombolysis in cerebral infarction scale, which categorizes the success of recanalization, achieved through mechanical thrombectomy. In our proposal, this clinical information is considered at two levels. First, at a population level by embedding the clinical information in a custom loss function used during training of our deep learning architecture. Second, at a patient-level through an extra input channel of the neural network used at testing time for a given patient case. By merging imaging with non-imaging clinical information, we aim to obtain a model aware of the principal and collateral blood flow dynamics for cases where there is no perfusion beyond the point of occlusion and for cases where the perfusion is complete after the occlusion point.

Local spatio-temporal encoding of raw perfusion MRI for the prediction of final lesion in stroke

We address the medical image analysis issue of predicting the final lesion in stroke from early perfusion magnetic resonance imaging. The classical processing approach for the dynamical perfusion images consists in a temporal deconvolution to improve the temporal signals associated with each voxel before performing prediction. We demonstrate here the value of exploiting directly the raw perfusion data by encoding the local environment of each voxel as a spatio-temporal texture, with an observation scale larger than the voxel. As a first illustration for this approach, the textures are characterized with local binary patterns and the classification is performed using a standard support vector machine (SVM). This simple machine learning classification scheme demonstrates results with 95% accuracy on average while working only raw perfusion data. We discuss the influence of the observation scale and evaluate the interest of using post-processed perfusion data with this approach.

Case-control comparison brain lesion segmentation for early infarct detection

Computed Tomography (CT) images are widely used for the identification of abnormal brain tissues following infarct and hemorrhage of a stroke. The treatment of this medical condition mainly depends on doctors' experience. While manual lesion delineation by medical doctors is currently considered as the standard approach, it is time-consuming and dependent on each doctor's expertise and experience. In this study, a case-control comparison brain lesion segmentation (CCBLS) method is proposed to segment the region pertaining to brain injury by comparing the voxel intensity of CT images between control subjects and stroke patients. The method is able to segment the brain lesion from the stacked CT images automatically without prior knowledge of the location or the presence of the lesion. The aim is to reduce medical doctors' burden and assist them in making an accurate diagnosis. A case study with 300 sets of CT images from control subjects and stroke patients is conducted. Comparing with other existing methods, the outcome ascertains the effectiveness of the proposed method in detecting brain infarct of stroke patients.

White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks

White matter hyperintensities (WMH) are a feature of sporadic small vessel disease also frequently observed in magnetic resonance images (MRI) of healthy elderly subjects. The accurate assessment of WMH burden is of crucial importance for epidemiological studies to determine association between WMHs, cognitive and clinical data; their causes, and the effects of new treatments in randomized trials. The manual delineation of WMHs is a very tedious, costly and time consuming process, that needs to be carried out by an expert annotator (e.g. a trained image analyst or radiologist). The problem of WMH delineation is further complicated by the fact that other pathological features (i.e. stroke lesions) often also appear as hyperintense regions. Recently, several automated methods aiming to tackle the challenges of WMH segmentation have been proposed. Most of these methods have been specifically developed to segment WMH in MRI but cannot differentiate between WMHs and strokes. Other methods, capable of distinguishing between different pathologies in brain MRI, are not designed with simultaneous WMH and stroke segmentation in mind. Therefore, a task specific, reliable, fully automated method that can segment and differentiate between these two pathological manifestations on MRI has not yet been fully identified. In this work we propose to use a convolutional neural network (CNN) that is able to segment hyperintensities and differentiate between WMHs and stroke lesions. Specifically, we aim to distinguish between WMH pathologies from those caused by stroke lesions due to either cortical, large or small subcortical infarcts. The proposed fully convolutional CNN architecture, called uResNet, that comprised an analysis path, that gradually learns low and high level features, followed by a synthesis path, that gradually combines and up-samples the low and high level features into a class likelihood semantic segmentation. Quantitatively, the proposed CNN architecture is shown to outperform other well established and state-of-the-art algorithms in terms of overlap with manual expert annotations. Clinically, the extracted WMH volumes were found to correlate better with the Fazekas visual rating score than competing methods or the expert-annotated volumes. Additionally, a comparison of the associations found between clinical risk-factors and the WMH volumes generated by the proposed method, was found to be in line with the associations found with the expert-annotated volumes.

•

Robust, fully automatic white matter hyperintensity and stroke lesion segmentation and differentiation

•

A novel patch sampling strategy used during CNN training that avoids the introduction of erroneous locality assumptions

•

Improved segmentation accuracy in terms of Dice scores when compared to well established state-of-the-art methods

Fully automated stroke tissue estimation using random forest classifiers (FASTER)

Several clinical trials have recently proven the efficacy of mechanical thrombectomy for treating ischemic stroke, within a six-hour window for therapy. To move beyond treatment windows and toward personalized risk assessment, it is essential to accurately identify the extent of tissue-at-risk ("penumbra"). We introduce a fully automated method to estimate the penumbra volume using multimodal MRI (diffusion-weighted imaging, a T2w- and T1w contrast-enhanced sequence, and dynamic susceptibility contrast perfusion MRI). The method estimates tissue-at-risk by predicting tissue damage in the case of both persistent occlusion and of complete recanalization. When applied to 19 test cases with a thrombolysis in cerebral infarction grading of 1-2a, mean overestimation of final lesion volume was 30 ml, compared with 121 ml for manually corrected thresholding. Predicted tissue-at-risk volume was positively correlated with final lesion volume ( p < 0.05). We conclude that prediction of tissue damage in the event of either persistent occlusion or immediate and complete recanalization, from spatial features derived from MRI, provides a substantial improvement beyond predefined thresholds. It may serve as an alternative method for identifying tissue-at-risk that may aid in treatment selection in ischemic stroke.